Files
myWiki/concepts/governance-security.md
2026-06-01 10:46:01 +08:00

39 lines
1.5 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: "Governance & Security治理与安全"
created: 2026-05-23
updated: 2026-05-23
type: concept
tags: [agent, governance, security, compliance, audit, identity]
sources: [raw/papers/agent-harness-engineering-survey-2026.md]
confidence: high
---
# Governance & SecurityG 层)
> ETCLOVG 的 G 层:通过权限、身份、策略、加固、审计和人类监督机制约束 Agent 行为。覆盖三个治理子层。
## 三个治理子层
1. **模型级Model-Level**护栏guardrails、内容过滤器、constitutional AI
2. **系统级System-Level**网关gateways、代理proxies、权限模型permission models
3. **组织级Organizational-Level**审计audit、合规compliance、人机协同human-in-the-loop
## 关键组件
- **权限模型与身份管理**Agent 身份、委托、权限清单
- **生命周期 Hook**:在关键决策点插入治理检查
- **组件加固**沙箱逃逸防护、prompt injection 防御
- **声明式宪法**:如 Claude's ConstitutionAnthropic, 2026a
- **审计基础设施**:记录所有 Agent 操作以供审查
## 与 [[capability-control-tradeoff]] 的关系
G 层是 control 侧的集中体现。更强的工具和更宽松的沙箱每扩展一次能力G 层就需要相应增强审计粒度、权限边界和恢复能力。
## 相关概念
- [[etclovg-taxonomy]]
- [[capability-control-tradeoff]]
- [[standard-agent-handoffs]] — 交接中的责任转移
- [[agent-harness-engineering-survey]]